RESUMEN
Too often, the testing and evaluation of object detection, as well as the classification techniques for high-resolution remote sensing imagery, are confined to clean, discretely partitioned datasets, i.e., the closed-world model. In recent years, the performance on a number of benchmark datasets has exceeded 99% when evaluated using cross-validation techniques. However, real-world remote sensing data are truly big data, which often exceed billions of pixels. Therefore, one of the greatest challenges regarding the evaluation of machine learning models taken out of the clean laboratory setting and into the real world is the difficulty of measuring performance. It is necessary to evaluate these models on a grander scale, namely, tens of thousands of square kilometers, where it is intractable to the ground truth and the ever-changing anthropogenic surface of Earth. The ultimate goal of computer vision model development for automated analysis and broad area search and discovery is to augment and assist humans, specifically human-machine teaming for real-world tasks. In this research, various models have been trained using object classes from benchmark datasets such as UC Merced, PatternNet, RESISC-45, and MDSv2. We detail techniques to scan broad swaths of the Earth with deep convolutional neural networks. We present algorithms for localizing object detection results, as well as a methodology for the evaluation of the results of broad-area scans. Our research explores the challenges of transitioning these models out of the training-validation laboratory setting and into the real-world application domain. We show a scalable approach to leverage state-of-the-art deep convolutional neural networks for the search, detection, and annotation of objects within large swaths of imagery, with the ultimate goal of providing a methodology for evaluating object detection machine learning models in real-world scenarios.
RESUMEN
The adoption of clean cooking technologies goes beyond mere product acquisition and requires attention to issues of cooking traditions, user engagement, gender dynamics, culture, and religion to effect correct and consistent use.
Asunto(s)
Contaminación del Aire Interior/prevención & control , Culinaria/instrumentación , Artículos Domésticos/instrumentación , Países en Desarrollo , Diseño de Equipo , Humanos , Mercadotecnía/métodosRESUMEN
The Hyperspectral Imager for the Coastal Ocean (HICO) is the first spaceborne hyperspectral sensor designed specifically for the coastal ocean and estuarial, riverine, or other shallow-water areas. The HICO generates hyperspectral images, primarily over the 400-900 nm spectral range, with a ground sample distance of ≈90 m (at nadir) and a high signal-to-noise ratio. The HICO is now operating on the International Space Station (ISS). Its cross-track and along-track fields of view are 42 km (at nadir) and 192 km, respectively, for a total scene area of 8000 km(2). The HICO is an innovative prototype sensor that builds on extensive experience with airborne sensors and makes extensive use of commercial off-the-shelf components to build a space sensor at a small fraction of the usual cost and time. Here we describe the instrument's design and characterization and present early images from the ISS.
RESUMEN
As the availability of various geospatial data increases, there is an urgent need to integrate multiple datasets to improve spatial analysis. However, since these datasets often originate from different sources and vary in spatial accuracy, they often do not match well to each other. In addition, the spatial discrepancy is often nonsystematic such that a simple global transformation will not solve the problem. Manual correction is labor-intensive and time-consuming and often not practical. In this paper, we present an innovative solution for a vector-to-imagery conflation problem by integrating several vector-based and image-based algorithms. We only extract the different types of road intersections and terminations from imagery based on spatial contextual measures. We eliminate the process of line segment detection which is often troublesome. The vector road intersections are matched to these detected points by a relaxation labeling algorithm. The matched point pairs are then used as control points to perform a piecewise rubber-sheeting transformation. With the end points of each road segment in correct positions, a modified snake algorithm maneuvers intermediate vector road vertices toward a candidate road image. Finally a refinement algorithm moves the points to center each road and obtain better cartographic quality. To test the efficacy of the automated conflation algorithm, we used U.S. Census Bureau's TIGER vector road data and U.S. Department of Agriculture's 1-m multi-spectral near infrared aerial photography in our study. Experiments were conducted over a variety of rural, suburban, and urban environments. The results demonstrated excellent performance. The average correctness measure increased from 20.6% to 95.5% and the average root-mean-square error decreased from 51.2 to 3.4 m.
Asunto(s)
Algoritmos , Bases de Datos Factuales , Sistemas de Información Geográfica , Aumento de la Imagen/métodos , Interpretación de Imagen Asistida por Computador/métodos , Mapas como Asunto , Reconocimiento de Normas Patrones Automatizadas/métodos , Inteligencia Artificial , Reproducibilidad de los Resultados , Sensibilidad y EspecificidadRESUMEN
Antarctic Ice Sheet elevation changes, which are used to estimate changes in the mass of the interior regions, are caused by variations in the depth of the firn layer. We quantified the effects of temperature and accumulation variability on firn layer thickness by simulating the 1980-2004 Antarctic firn depth variability. For most of Antarctica, the magnitudes of firn depth changes were comparable to those of observed ice sheet elevation changes. The current satellite observational period ( approximately 15 years) is too short to neglect these fluctuations in firn depth when computing recent ice sheet mass changes. The amount of surface lowering in the Amundsen Sea Embayment revealed by satellite radar altimetry (1995-2003) was increased by including firn depth fluctuations, while a large area of the East Antarctic Ice Sheet slowly grew as a result of increased accumulation.
RESUMEN
Searching for relevant knowledge across heterogeneous geospatial databases requires an extensive knowledge of the semantic meaning of images, a keen eye for visual patterns, and efficient strategies for collecting and analyzing data with minimal human intervention. In this paper, we present our recently developed content-based multimodal Geospatial Information Retrieval and Indexing System (GeoIRIS) which includes automatic feature extraction, visual content mining from large-scale image databases, and high-dimensional database indexing for fast retrieval. Using these underpinnings, we have developed techniques for complex queries that merge information from heterogeneous geospatial databases, retrievals of objects based on shape and visual characteristics, analysis of multiobject relationships for the retrieval of objects in specific spatial configurations, and semantic models to link low-level image features with high-level visual descriptors. GeoIRIS brings this diverse set of technologies together into a coherent system with an aim of allowing image analysts to more rapidly identify relevant imagery. GeoIRIS is able to answer analysts' questions in seconds, such as "given a query image, show me database satellite images that have similar objects and spatial relationship that are within a certain radius of a landmark."
RESUMEN
Satellite radar altimetry measurements indicate that the East Antarctic ice-sheet interior north of 81.6 degrees S increased in mass by 45 +/- 7 billion metric tons per year from 1992 to 2003. Comparisons with contemporaneous meteorological model snowfall estimates suggest that the gain in mass was associated with increased precipitation. A gain of this magnitude is enough to slow sea-level rise by 0.12 +/- 0.02 millimeters per year.